© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15443
    Prev
    Next
    INDEX
    Explanations

    specific materials and their unique features in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    high-value or luxury materials like precious metals, fine textiles, gourmet foods, and premium automotive components.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProtoMessage
    -0.60
     initComponents
    -0.59
    PHIA
    -0.51
    ThroughAttribute
    -0.50
    PerformLayout
    -0.47
     Empowerment
    -0.46
    minecraftforge
    -0.46
    tispiece
    -0.45
     Hort
    -0.45
     Pamphlet
    -0.44
    POSITIVE LOGITS
    SpringRunner
    0.51
    SBATCH
    0.42
     expensive
    0.41
    లాలు
    0.39
    Enllaces
    0.36
    const
    0.36
    expensive
    0.35
    GoogleApiClient
    0.35
    billon
    0.35
     Genau
    0.35
    Activations Density 0.255%

    No Known Activations